You're an infrastructure engineer, ideally with ML experience. We're growing fast and need your help scaling.
We serve machine learning models. We deal with GPUs, optimize models, write prediction servers, set up clusters, and so on. All the hard stuff that companies doing ML would rather not deal with.
Instead of being an ML infrastructure engineer at a single product company, work for us and force-multiply yourself across thousands of companies.
We're looking for the right person, not just someone who checks boxes, so you don't need to satisfy all these things. But, you might have some of these qualities:
- Experience building and scaling infrastructure at huge scale.
- You can squeeze every last drop of performance out of a GPU.
- You know your way out of
CUDA error: device-side assert triggered.
- Excellent communication skills. We think most of being a programmer is not programming. We want you to be able to communicate complex topics clearly, write down your thinking, write good docs, etc.
Replicate
